data-analysis

Identify patterns in datasets to inform decisions with reproducible steps.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/kirillshilin/instructions --skill data-analysis-kirillshilin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-analysis
Source: https://github.com/kirillshilin/instructions/tree/main/obsolete/dotgithub/skills/data-analysis
Command: npx skills add https://github.com/kirillshilin/instructions --skill data-analysis-kirillshilin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Collecting and interpreting data often requires time and expertise to uncover actionable insights. This skill helps you systematically explore datasets, identify key trends, and translate results into decisions.

Core Features & Use Cases

  • Profile data quality, shape, and distributions to understand the dataset context.
  • Write and validate queries or data-processing steps (SQL, Python, or BI tools) to answer specific questions.
  • Generate concise analyses and visualizations that support stakeholders and decision-makers.

Quick Start

Analyze the provided dataset to identify trends and produce a concise, actionable summary.

Frequently Asked Questions about data-analysis

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I profile data quality and identify trends in a dataset?

Data profiling examines dataset shape, distributions, and context to identify quality issues and key trends. This skill applies systematic exploration to translate results into concise, actionable summaries for stakeholder decisions.

Can I generate analytical queries in SQL and Python pandas?

Yes, you can write and validate analytical queries using SQL and Python pandas. The skill generates reproducible data-processing steps with guardrails to answer specific questions and validate results before communicating findings to stakeholders.

What's the best way to turn raw data into clear insights for stakeholders?

The best way to turn data into decisions is by generating concise analyses and visualizations that support decision-makers. This involves profiling data quality, writing validated queries, and communicating findings with reproducible steps and guardrails.

Does this data analysis approach support reproducible workflows and guardrails?

Yes, this approach supports reproducible steps and guardrails throughout the data analysis workflow. It validates results from analytical queries and data-processing steps, ensuring findings communicated to stakeholders are reliable and systematically generated.

What are the limitations of automated data profiling for decision-making?

Automated data profiling illuminates patterns and distributions but requires contextual understanding to inform decisions accurately. While it generates validated queries and visualizations, stakeholders must interpret findings within their specific business context for effective decision-making.